Image Style Transfer in Deep Learning Networks
Title | Image Style Transfer in Deep Learning Networks |
Publication Type | Conference Paper |
Year of Publication | 2018 |
Authors | Li, Y., Zhang, T., Han, X., Qi, Y. |
Conference Name | 2018 5th International Conference on Systems and Informatics (ICSAI) |
Keywords | ART, artistic styles, classical style migration model, CNN, Computer vision, computer vision researchers, convolution neural network, convolutional neural nets, Deep Learning, deep learning network development process, Image color analysis, image recognition, image style transfer, images contents, learning (artificial intelligence), Neural networks, neural style transfer, Painting, Predictive Metrics, pubcrawl, Resiliency, Scalability, Semantics |
Abstract | Since Gatys et al. proved that the convolution neural network (CNN) can be used to generate new images with artistic styles by separating and recombining the styles and contents of images. Neural Style Transfer has attracted wide attention of computer vision researchers. This paper aims to provide an overview of the style transfer application deep learning network development process, and introduces the classical style migration model, on the basis of the research on the migration of style of the deep learning network for collecting and organizing, and put forward related to gathered during the investigation of the problem solution, finally some classical model in the image style to display and compare the results of migration. |
DOI | 10.1109/ICSAI.2018.8599501 |
Citation Key | li_image_2018 |
- convolution neural network
- Semantics
- Painting
- Neural networks
- learning (artificial intelligence)
- images contents
- image style transfer
- image recognition
- Image color analysis
- deep learning network development process
- deep learning
- convolutional neural nets
- neural style transfer
- computer vision researchers
- computer vision
- CNN
- classical style migration model
- artistic styles
- ART
- pubcrawl
- Predictive Metrics
- Resiliency
- Scalability